Summary of Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-free Ensembles Of Dnns, by Uri Stern et al.
Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs
by Uri Stern, Daphna Weinshall
First submitted to arxiv on: 17 Oct 2023
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The novel score for quantifying overfit introduced in this paper measures the forgetting rate of deep models on validation data. The study reveals that overfit can occur with or without a decrease in validation accuracy, and may be more common than previously appreciated. This observation is used to construct a new ensemble method based solely on the training history of a single network, which provides significant improvement in performance without any additional cost in training time. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about how deep neural networks can sometimes become too good at recognizing specific patterns in their training data, even though they should be getting worse. The researchers found that this can happen even if the model gets better and better on its main task. They came up with a new way to measure when this happens, and used it to create a new method for combining the predictions of different models. This new method works well on many different kinds of data and neural networks. |
